"Sparse Autoencoders Find Highly Interpretable Features in Language Models."

Robert Huben et al. (2024)

> Home

Details and statistics

DOI: —

access: open

type: Conference or Workshop Paper

metadata version: 2024-08-07

- view
  - electronic edition @ openreview.net (open access)
- export record
  dblp key:
  - conf/iclr/HubenCRES24
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/iclr/HubenCRES24
Robert Huben, Hoagy Cunningham, Logan Riggs, Aidan Ewart, Lee Sharkey:
Sparse Autoencoders Find Highly Interpretable Features in Language Models. ICLR 2024

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.